CT Texture Analysis of Renal Masses

Raman, Siva P.; Chen, Yifei; Schroeder, James L.; Huang, Peng; Fishman, Elliot K.

doi:10.1016/j.acra.2014.07.023

Cited by 149 publications

(40 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…an expected result, as RFs are known to perform well in smaller data settings as they are fairly robust to noise." A RF has also been used to predict renal mass pathology on CT (40).…”

Section: Random Forestsmentioning

confidence: 99%

Machine Learning Principles for Radiology Investigators

Borstelmann

2020

Academic Radiology

View full text Add to dashboard Cite

“…an expected result, as RFs are known to perform well in smaller data settings as they are fairly robust to noise." A RF has also been used to predict renal mass pathology on CT (40).…”

Section: Random Forestsmentioning

confidence: 99%

Machine Learning Principles for Radiology Investigators

Borstelmann

2020

Academic Radiology

View full text Add to dashboard Cite

“…Texture analysis (TA) extracts local variations in pixel intensities using well-established mathematical formulas and provides a set of quantifiable metrics that may supplement radiologists' qualitative image interpretations. Research suggests that TA may be of particular value for the differentiation of tumours with similar imaging characteristics on conventional imaging [19-23]. …”

Section: Introductionmentioning

confidence: 99%

Differentiation of Uterine Leiomyosarcoma from Atypical Leiomyoma: Diagnostic Accuracy of Qualitative MR Imaging Features and Feasibility of Texture Analysis

et al. 2016

View full text Add to dashboard Cite

Purpose To investigate whether qualitative magnetic resonance (MR) features can distinguish leiomyosarcoma (LMS) from atypical leiomyoma (ALM) and assess the feasibility of texture analysis (TA). Methods This retrospective study included 41 women (ALM=22, LMS=19) imaged with MRI prior to surgery. Two readers (R1, R2) evaluated each lesion for qualitative MR features. Associations between MR features and LMS were evaluated with Fisher's exact test. Accuracy measures were calculated for the four most significant features. TA was performed for 24 patients (ALM=14, LMS=10) with uniform imaging following lesion segmentation on axial T2-weighted images. Texture features were pre-selected using Wilcoxon signed-rank test with Bonferroni correction and analyzed with unsupervised clustering to separate LMS from ALM. Results Four qualitative MR features most strongly associated with LMS were nodular borders, haemorrhage, “T2 dark” area(s), and central unenhanced area(s) (p≤0.0001 each feature/reader). The highest sensitivity [1.00 (95%CI:0.82-1.00)/0.95 (95%CI: 0.74-1.00)] and specificity [0.95 (95%CI:0.77-1.00)/1.00 (95%CI:0.85-1.00)] were achieved for R1/R2, respectively, when a lesion had ≥3 of these four features. Sixteen texture features differed significantly between LMS and ALM (p-values: <0.001-0.036). Unsupervised clustering achieved accuracy of 0.75 (sensitivity: 0.70; specificity: 0.79). Conclusions Combination of ≥3 qualitative MR features accurately distinguished LMS from ALM. TA was feasible.

show abstract

“…Nonetheless, it is important for practicing radiologists to be aware of the existence of HOCTs and other benign/indolent renal masses that can mimic aggressive tumors. This is because promising, new, noninvasive means of characterizing renal masses are beginning to appear in the literature at both the preclinical 18 and early clinical 19–21 stages of development. In the near future, it is likely that characterization of renal masses will rely on information from both traditional cross-sectional methods as well as more functional and metabolic aspects of the tumors.…”

Section: Discussionmentioning

confidence: 99%

Computed Tomography Appearance of Renal Hybrid Oncocytic/Chromophobe Tumors

Bhatnagar

Rowe²,

Gorin³

et al. 2016

Journal of Computer Assisted Tomography

Self Cite

View full text Add to dashboard Cite

Objective A series of renal hybrid oncocytic/chromophobe tumors (HOCTs) was retrospectively assessed for morphologic features and enhancement characteristics by computed tomography (CT). Materials (Subjects) and Methods Nine patients with pathologically proven HOCTs were identified. These patients harbored a total of 12 lesions. All patients had available preoperative contrast-enhanced CT examinations, although a proportion of the studies had been carried out at outside institutions. The morphologic characteristics and enhancement patterns of each tumor were evaluated systematically. Results Seventy-eight percent of the patients were men, with a mean age of 62 years. None of the patients had evidence of metastatic disease at the time of surgery. Mean tumor diameter was 4.4 cm. All the lesions were solid and well circumscribed. Calcifications were not seen in any of these masses. Thirty-three percent of the tumors demonstrated a central stellate hypodensity pattern, whereas a further 42% of the tumors demonstrated a heterogenous appearance. Mean attenuation values were 25.7 HU (noncontrast), 77.4 HU (arterial), 124.8 HU (venous), and 76.8 HU (delayed). Tumor-to-cortex ratios for the 2 enhanced phases (arterial and venous) were 0.56 and 0.79, respectively. Conclusions A series of HOCTs were found on CT to have 2 distinct patterns—a heterogenous enhancement pattern and an “oncocytoma-like” pattern with a central stellate hypodensity. Although the prospective diagnosis of HOCTs on the basis of CT findings is unlikely, an awareness of the existence of these lesions is important as new means of characterizing renal masses on imaging arise.

show abstract

CT Texture Analysis of Renal Masses

Cited by 149 publications

References 40 publications

Machine Learning Principles for Radiology Investigators

Machine Learning Principles for Radiology Investigators

Differentiation of Uterine Leiomyosarcoma from Atypical Leiomyoma: Diagnostic Accuracy of Qualitative MR Imaging Features and Feasibility of Texture Analysis

Computed Tomography Appearance of Renal Hybrid Oncocytic/Chromophobe Tumors

Contact Info

Product

Resources

About